Model: GELU Model: 1 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1562 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.9881. Min Range: -3.9881

Max Act: 3.9881. Min Act: -0.1700

Data Index: 52046 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 3.9881. Min Range: -3.9881

Max Act: 3.9123. Min Act: -0.1700

Data Index: 794399 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 3.9881. Min Range: -3.9881

Max Act: 3.8701. Min Act: -0.1700

Data Index: 1136485 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 3.9881. Min Range: -3.9881

Max Act: 3.8523. Min Act: -0.1700

Data Index: 406941 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 3.9881. Min Range: -3.9881

Max Act: 3.8741. Min Act: -0.1700

Data Index: 268860 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 3.9881. Min Range: -3.9881

Max Act: 3.8446. Min Act: -0.1700

Data Index: 660227 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 3.9881. Min Range: -3.9881

Max Act: 3.8177. Min Act: -0.1700

Data Index: 378290 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 3.9881. Min Range: -3.9881

Max Act: 3.8264. Min Act: -0.1700

Data Index: 725122 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 3.9881. Min Range: -3.9881

Max Act: 3.8231. Min Act: -0.1700

Data Index: 838671 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 3.9881. Min Range: -3.9881

Max Act: 3.8184. Min Act: -0.1700

Data Index: 564672 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 3.9881. Min Range: -3.9881

Max Act: 3.8243. Min Act: -0.1700

Data Index: 1107118 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 3.9881. Min Range: -3.9881

Max Act: 3.8004. Min Act: -0.1700

Data Index: 1324605 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 3.9881. Min Range: -3.9881

Max Act: 3.7911. Min Act: -0.1700

Data Index: 249088 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 3.9881. Min Range: -3.9881

Max Act: 3.7774. Min Act: -0.1700

Data Index: 822259 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 3.9881. Min Range: -3.9881

Max Act: 3.7444. Min Act: -0.1700

Data Index: 609726 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 3.9881. Min Range: -3.9881

Max Act: 3.7999. Min Act: -0.1700

Data Index: 742255 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 3.9881. Min Range: -3.9881

Max Act: 3.7876. Min Act: -0.1700

Data Index: 450856 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 3.9881. Min Range: -3.9881

Max Act: 3.7985. Min Act: -0.1700

Data Index: 1267576 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 3.9881. Min Range: -3.9881

Max Act: 3.7849. Min Act: -0.1700

Data Index: 199593 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 3.9881. Min Range: -3.9881

Max Act: 3.7714. Min Act: -0.1700

Data Index: 706956 (C4 (Web Text))

Max Activating Token Index: 747